World Labs Rolls Out Beta Access to Its Atlas AI World Builder
Creators can build 3D scenes from reference images, set precise camera paths, and reuse generated views to extend a world.
World Labs has begun rolling out beta access to Atlas (opens in a new tab), its AI model for generating and reconstructing 3D scenes, the company announced on October 15 (opens in a new tab).
Atlas accepts camera positions and angles directly, so creators can define a shot’s path in 3D instead of relying on a written prompt to describe the movement.
World Labs’ developer documentation (opens in a new tab) shows how generated views can be reused, with their camera and depth data, as context for later shots. For real locations, more reference photographs reduce how much unseen detail the model has to invent.
World Labs introduced Atlas in September (opens in a new tab) with both video and 3D output, including Gaussian splats, the scene format used in Marble. Atlas is intended to power future versions of that app.
Creators can request beta access (opens in a new tab) through World Labs’ waitlist. The company says it will email applicants when access is available.
More from Capture & Create.
Browse all stories
3D capture · 2 min read
Gracia Says Its New AI Creates 3D Replays With as Few as Four Cameras
The World Reconstruction Model promises near real-time sports replays, with broader uses in film effects, 4D capture, and robot training.
Blockworks · 2 min read
Blockworks Turns Your Words Into Builds with AI on Apple Vision Pro
A new AI demo makes a boat, a bicycle picture, and a statue from virtual blocks you can pick up and take apart.
Tripo AI · 4 min read
Tripo Adds 3D Animation From Text Prompts
Creators can generate short actions from prompts and combine up to five motion segments, with skeleton options for Unreal Engine, Unity, and avatar workflows.